Triadic Concept Analysis for Logic Interpretation of Simple Artificial Networks

TL;DR

This paper introduces a method to interpret simple neural networks by converting them into symbolic logic trees using Formal Concept Analysis, maintaining their classification accuracy.

Contribution

It presents a novel approach to derive interpretable symbolic representations from ReLU-based neural networks using triadic concept analysis.

Findings

The method preserves the original classification accuracy.

It produces interpretable logic trees from neural network models.

The approach effectively bridges neural networks and symbolic reasoning.

Abstract

An artificial neural network (ANN) is a numerical method used to solve complex classification problems. Due to its high classification power, the ANN method often outperforms other classification methods in terms of accuracy. However, an ANN model lacks interpretability compared to methods that use the symbolic paradigm. Our idea is to derive a symbolic representation from a simple ANN model trained on minterm values of input objects. Based on ReLU nodes, the ANN model is partitioned into cells. We convert the ANN model into a cell-based, three-dimensional bit tensor. The theory of Formal Concept Analysis applied to the tensor yields concepts that are represented as logic trees, expressing interpretable attribute interactions. Their evaluations preserve the classification power of the initial ANN model.